GPT 4.5
OpenAI
Highlights
Top benchmark results for openai/gpt-4-5-2025-02-27.
3066#3
0.45#25
0.37#35
0.10#24
0.01#17
13.64#11
6.28#4
1093#19
0.71#33
220#6
0.59#12
1434#4
0.34#16
0.34#15
0.38#18
1.93#12
Benchmark table
Detailed scores across tracked benchmarks.
| Benchmark | Category | Top Score | Info | Self Reported | Source |
|---|---|---|---|---|---|
| AidanBench | - | 3066 | - | No | Source |
| Aider-Polyglot | code | 0.45 | - | No | Source |
| AIME 2024 | math | 0.37 | - | Yes | Source |
| ARC-AGI-1 | - | 0.10 | - | No | Source |
| ARC-AGI-2 | - | 0.01 | - | No | Source |
| Confabulations | - | 13.64 | - | No | Source |
| Elimation Game | - | 6.28 | - | No | Source |
| EQ-Bench 3 | - | 1093 | - | No | Source |
| GPQA Diamond | general-knowledge | 0.71 | - | Yes | - |
| LisanBench | - | 220 | - | No | Source |
| LiveBench | - | 0.59 | - | No | Source |
| LMArena Text | - | 1434 | - | No | Source |
| NYT Connections | - | 0.34 | - | No | Source |
| SimpleBench | - | 0.34 | - | No | Source |
| SWE-Bench | code | 0.38 | - | Yes | Source |
| Thematic Generalisation | - | 1.93 | - | No | Source |
Benchmark comparisons
Use the selector to switch benchmarks and see how this model stacks up against its closest competitors.
SWE-Bench
Compare this model with the leading peers for the selected benchmark.
Benchmark
0.38
Rank #18/21
21 models
Showing 11 models around the selected model (out of 21 total).